检索结果-内蒙古大学图书馆

Proceedings of the 5th International Conference on Information Management & Machine intelligence

作者： Anjul Bhardwaj Uday Pratap Singh Artificial Intelligence & Data Science Poornima Institute of Engineering & Technology India Department of AI & DS Poornima Institute of Engineering and Technology India

ISBN: (纸本)9798400709418

The OHLCV (Open, High, Low, Close, Volume) data used in this study is used to forecast time series and anticipate stock price movement. We investigate a wide variety of models, including traditional statistical approaches and cutting-edge deep learning strategies combined with sentiment analysis, feature extraction, and hyperparameter tweaking. Instead of focusing on absolute stock prices, our main goal is to predict swings in stock prices, as this has been shown to produce more accurate outcomes. We start our research by obtaining historical Amazon stock data via the Yahoo API, and then we go on a thorough analytical journey. We generate features on the OHLCV data first, and then we design and test Fourier and Autoregressive Integrated Moving Average (ARIMA) models. We then switch to more sophisticated deep learning methods, using the pre-processed data to apply Long Short-Term Memory (LSTM) models. Interestingly, we add sentiment analysis to the LSTM study, which expands its scope and lets us consider market sentiment as a possible influencing factor. To guarantee the stability of our models, we use a careful train-test split technique and organize the data in a time series manner. The field of financial forecasting and trading methods will ultimately benefit from the insightful information our study's findings provide on the efficacy of different modeling techniques and their capacity to forecast stock price movements.

关键词： ARIMA (Autoregressive Integrated Moving Average)

来源：评论

学校读者我要写书评

暂无评论

Graph Regularized Sparse Non-Negative Matrix Factorization for Clustering

引用

IEEE Transactions on Computational Social Systems 2023年第3期10卷 910-921页

作者： Deng, Ping Li, Tianrui Wang, Hongjun Wang, Dexian Horng, Shi-Jinn Liu, Rui Southwest Jiaotong University National Engineering Laboratory of Integrated Transportation Big Data Application Technology School of Computing and Artificial Intelligence Chengdu611756 China National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei106 Taiwan North Sichuan Medical College School of Preclinical Medicine Department of Computer and Mathematics Nanchong637100 China

The graph regularized nonnegative matrix factorization (GNMF) algorithms have received a lot of attention in the field of machine learning and data mining, as well as the square loss method is commonly used to measure the quality of reconstructed data. However, noise is introduced when data reconstruction is performed;and the square loss method is sensitive to noise, which leads to degradation in the performance of data analysis tasks. To solve this problem, a novel graph regularized sparse NMF (GSNMF) is proposed in this article. To obtain a cleaner data matrix to approximate the high-dimensional matrix, the l1-norm to the low-dimensional matrix is added to achieve the adjustment of data eigenvalues in the matrix and sparsity constraint. In addition, the corresponding inference and alternating iterative update algorithm to solve the optimization problem are given. Then, an extension of GSNMF, namely, graph regularized sparse nonnegative matrix trifactorization (GSNMTF), is proposed, and the detailed inference procedure is also shown. Finally, the experimental results on eight different datasets demonstrate that the proposed model has a good performance. © 2014 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Introducing the Hyperdynamic Adaptive Learning Fusion (HALF) model for superior predictive analytics in E-learning

引用

Neural Computing and Applications 2025年 1-21页

作者： Islam, Umar Alali, Ibrahim Khalil Alotaibi, Shoayee Dlaim Alzaid, Zaid Shah, Babar Ali, Ijaz Moreira, Fernando Department of Computer Science IQRA National University Swat Campus Peshawar Pakistan Department of Instructional Technology Jouf University Sakaka Saudi Arabia Department of Artificial Intelligence and Data Science University of Hail Hail Saudi Arabia Faculty of Computer Science and Information Systems Islamic University of Madinah Madinah42351 Saudi Arabia College of Technological Innovation Zayed University Dubai United Arab Emirates REMIT Portucalense University & IEETA Aveiro University Aveiro Portugal

Today’s complex world is defined by digital changes in educational paradigms to which E-learning has contributed significantly, and as such, accurate prediction methods are needed for student performance modeling. In this paper a new and complex model is proposed, namely the Hyperdynamic Adaptive Learning Fusion (HALF) model that leverages adaptive computing paradigms and artificial intelligence to build a fusion of learning that adapts to the new learning patterns. Many conventional predictive models employ linear and simplistic relationships to predict an outcome from an input;hence, they fail to decompose complex and heterogenic data patterns of educational data and also suffer from scalability issues for dealing with large volumes of data. To overcome these issues, the HALF model employs the relevant ensemble learning algorithms that consist of bagging, boosting, and an innovative adaptive fusion strategy that integrates base and adaptive models to achieve higher accuracy and resilience in the latter. In doing so, and by adopting the scientific method of working on trials and errors and rigorous assessment employing a database derived from the Open University VLE, the investigation presented in this paper provides compelling evidence of the HALF model’s superior efficacy, which yields an accuracy of 87%. 2%, precision of 85. 4% It has been proved that 3% of all students have significant learning disabilities, while the recall value is 89. 1%, surpassing traditional methods. The model’s equation can be easily applied to any variety of courses and of students, which makes it highly beneficial to educators and administrators;at the same time, the model is highly interpretable. Therefore, HALF model proves to be a revolutionary addition to the current kind of statistical modeling in E-learning that depicts student engagement pattern into more precise and accurate form, reduce biases in all way possible and provides solution that might help to improve the course outc

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Integrating Deep Learning and data science: Challenges, Opportunities and Implications 15

Integrating Deep Learning and Data Science: Challenges, Oppo...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Agarwal, Ankita Patil, Nagaraj Rajeswari, M. Yadav, Gitanjali B. Mishra, Rahul Sood, Gourav Maharishi University of Information Technology Maharishi School of Engineering and Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Mechanical Engineering Karnataka Ramnagar District562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India Chitkara University Institute of Engineering and technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350370249

Deep gaining knowledge of and records science are the most important and surprisingly influential fields of technology. Deep studying can system extensive statistics to discover styles, create insights, and have their personal choices concerning further analysis. Facts and technological know-how are centered on information-pushed business selection-making, using predictive analytics, machine studying, and other more recent algorithms to perceive, refine, and increase intelligent choices based on information. Those fields are rapidly developing and overlapping, creating an ever-increasing demand for each technical professionals and people with an intensive knowledge of statistics science and deep mastering. Integrating deep gaining knowledge of and records technology can create some challenges and possibilities which have to be explored. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Identity-Based Access Control in IoT: Enhancing Security through Mutual Cryptographic Authentication and Context Awareness 3

Identity-Based Access Control in IoT: Enhancing Security thr...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： More, Priyanka Sakhare, Sachin Mahalle, Parikshit Smt. Kashibai Navale College of Engineering Department of Computer Engineering Vishwakarma Institute of Information Technology Pune India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Vishwakarma Institute of Information Technology Department of Artificial Intelligence and Data Science Pune India

ISBN: (纸本)9798350317022

The proposed methodology strengthens security and privacy in IoT networks through mutual cryptographic authentication, employing Elliptic Curve Cryptography, Diffe Hellman for key exchange, and encryption methods for robust identity verification. Context awareness, considering factors like device type, communication type, successful transfers, and device behaviour, enhances access control decisions dynamically. This approach bolsters network security, defending against unauthorized access and potential threats. Identity-based access control streamlines access rights management, dynamically setting permissions for scalable network expansion. Combining cryptographic authentication and context sensitivity, this methodology emerges as a potent tool for securing IoT networks, ensuring data integrity, and preserving user privacy. Its versatility makes it applicable across diverse loT scenarios, offering a flexible and scalable access control solution. Overall, devices get authenticated with each other through identity based on clusters formed by context parameters and access rights are set to the cluster head. The cluster head is dynamically updated from time to time considering the context parameters. © 2023 IEEE.

关键词： context clustering decryption Elliptic Curve Cryptography encryption identity-based access control

来源：评论

学校读者我要写书评

暂无评论

Detection of Mango Leaves Disease using CSUBW based Residual Attention with EfficientNet 2

Detection of Mango Leaves Disease using CSUBW based Residual...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Kumar V, Sunil Jyothi, A.P. Nagamani, H.S. Sumanth, S. Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Ramaiah University of Applied Sciences Faculty of Engineering and Technology Department of Cse Bengaluru India Department of Computer Science Bengaluru India Department of Computer Science and Computer Applications Kolar India

ISBN: (纸本)9798350382952

Mangoes are one of the most popular fruits worldwide due to their taste and nutrition. Plant diseases may reduce plant quantity and quality. Disease management to improve crop quality and productivity requires early plant illness detection. Automation of plant disease detection reduces large farm surveillance. Since plants feed us, leaf problems must be diagnosed quickly and accurately. Our advanced learning method automatically detects leaf disease in several mango plant varieties. This study creates the RAM-EfficientNet, a novel illness classification network. The RAM block in EfficientNet extracts additional features and handles slight leaf lesion changes. Transfer learning was used to train EfficientNet on ImageNet to overcome the mango leaf disease sample size issue. The Cat Swarm Updated Black Widow Model (CSUBW), a hybrid optimization model, changes RAM-EfficientNet's weights to improve classification accuracy. Black Widow Optimization Algorithm (BWO) and Cat Swarm Optimization Algorithm (CSO) are combined to create the hybrid optimization model. The model's performance is then assessed to confirm its efficacy. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

New extended sidon spaces with dimension k+1 8

New extended sidon spaces with dimension k+1

引用

2024 8th International Conference on Mechanics, Mathematics and Applied Physics, ICMMAP 2024

作者： Wu, Lingling Li, Yu Fang, Lin Niu, Yongfeng College of Electrical Engineering Changzhou Vocational Institute of Mechatronic Technology Changzhou213164 China School of Computer Science and Artificial Intelligence and Aliyun School of Big Data Changzhou University Changzhou213164 China China Telecom Anhui Branch Hefei230071 China

In recent years, Sidon spaces have gained great popularity and applications in various fields such as multi-antenna communication systems, distributed storage systems, multimedia transmission, and network coding. With our further research into this field, it becomes evident that Sidon spaces are crucial in the field of constructing cyclic subspace codes. Currently, lots of papers focuse on how to construct Sidon spaces. Researchers find that through using the roots of irreducible polynomials and primitive elements over finite fields, we can sucessfully construct them. Based on the significant research conducted by previous scholars, we obtain several Sidon spaces which have new cardinality. Moreover, these Sidon spaces is beneficial to help us obtain better-performance subspace codes. © Published under licence by IOP Publishing Ltd.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Personalized Care for Multiple Sclerosis with IoT Wearables and Deep Learning

Personalized Care for Multiple Sclerosis with IoT Wearables ...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Vetriselvi, D. Sampathrajan, Rajeshkumar Deepa, A. Sujatha, V. Deepa, P. Pandi Murugan, S. Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai India McKinsey & Company Fort WorthTX United States Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai India Department of Electronics and Communication Engineering Shree Sathyam College of Engineering and Technology Tamil Nadu Salem India Department of Artificial Intelligence and Data Science Agni College of Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

ISBN: (纸本)9798350374933

This research work presents a new method for improving individualized treatment for patients with Multiple Sclerosis (MS) by combining Internet of Things (IoT) wearables with deep learning (DL) methods, namely Long Short-Term Memory (LSTM) networks. MS is a long-term autoimmune disorder that affects the central nervous system. It is marked by unexpected episodes of worsening symptoms and periods of improvement, highlighting the need for tailored therapy. The widespread use of IoT devices presents unique possibilities for the ongoing monitoring of many physiological and activity measurements important to the development and symptoms of MS. Using LSTM networks, which are very proficient in analyzing temporal sequences, create a prediction model that may anticipate exacerbations of MS symptoms and customize therapies appropriately. Through the analysis of longitudinal data obtained from IoT devices, our model acquires knowledge about unique patterns of illness development and treatment response. This knowledge allows us to create customized care plans for individuals. These paths include proactive activities such as adjusting medication, making lifestyle changes, and seeking early medical advice. The goal is to reduce the worsening of symptoms, improve the quality of life, and optimize treatment results for individuals with MS. The proposed method shows potential for transforming the treatment of MS by offering proactive and patient-centered therapy adaptable to individual requirements and the dynamics of the illness. © 2024 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

A Centralized Blockchain Architecture with Optimum Sharing 8

A Centralized Blockchain Architecture with Optimum Sharing

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Ramasamy, Viswanathan Padmapriya, S. Kavitha, G. Lekha, D. Kl Univrsity Department of Computer Science and Engineering Andhra Pradesh Gundoore India Velammal Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Department of Computer Science and Engineering Tamil Nadu Namakkal India Rmk College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350396638

The monolithic network architectures are used in Bitcoin and other big cryptos. Different hierarchical ways to protect the decentralized blockchain have been discussed to improve its usability. However, no debate in the literature on how an appropriate shard size can be calculated to optimize the output and how deceptive or unreliable nodes can affect the optimum shard size range. This study includes an exchange and authentication scheme for hierarchical blockchain architecture in order to fix these issues. The hierarchy splits the network nodes into many disjoint fragments, with most transfers unregulated between these shards. Taking into account the performance and precision of the transaction validation in the case of malicious or defective nodes, the optimum shard size is calculated. It ensures that most of the good shards are available with the right scale, according to the highest acceptable threshold of defective nodes. It also offers a method to distinguish damaged shards by overlapping a tiny proportion of purchases across all shields and discarding all transactions. The theoretical efficiency analysis and the influence of network sharing on performance were based on experimental findings conducted on Amazon EC-2 nodes. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Improved Deep Reinforcement Learning Based Resource Allocation for 5G and Beyond Networks in Edge Computing Environment 3

Improved Deep Reinforcement Learning Based Resource Allocati...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Balasm, Zaed Shashidhara, K.S. Sandhiyarajeshwari, B. Nigileeswari, B. Swarnalakshmi, G. College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India Rajalakshmi Institute of Technology Department of Artificial Intelligence & Data Science Poonamalle India Dhanalakshmi Srinivasan College Of Engineering Technology Department of Electronics and Communication Engineering Mamallapuram India New Prince Shri Bhavani College of Engineering and Technology Department of Mechanical Engineering Chennai India

ISBN: (纸本)9798331508456

Energy-efficient Resource Management (RM) for 5G and beyond networks has become challenging because of increasing Small Cells (SCs) densities and high Quality of Experience (QoE) requirements of business users. However, demands generated through plethora of innovations and concurrent IT services need high quality of service and quality of experience level overwhelm the resource available in 5G and Beyond scenarios. In this manuscript, developed the novel solution based on improved Deep Reinforcement Learning (DRL) which considers maximizing of overall value of data delivered to end users as coherent and comprehensive criterion of resource management. The developed algorithm has ability of learning efficient automatic resource management increasing total value delivered to end-users. The developed resource allocation and optimization technique addresses the changing user QoE requirements and minimizes energy consumption policies which allocates service metrics for in 5G networks. Based on simulations, it is clear that the developed method is highly effective and minimizes energy consumption to provide the QoE for users compared to conventional methods. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：